Industrial process operation state evaluation method based on supervision probability slow feature analysis

A technology of operating status and industrial process, applied in program control, comprehensive factory control, electrical test/monitoring, etc., can solve problems such as lack of evaluation of useless information, inaccurate extraction of process information, etc.

Pending Publication Date: 2022-05-24
CHINA UNIV OF MINING & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems existing in the above-mentioned prior art, the present invention provides an industrial process operating state evaluation method based on supervisory probability and slow feature analysis, which can effectively solve the problem of inaccurate process information extr

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Industrial process operation state evaluation method based on supervision probability slow feature analysis
  • Industrial process operation state evaluation method based on supervision probability slow feature analysis
  • Industrial process operation state evaluation method based on supervision probability slow feature analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0114] The present invention will be further described below.

[0115] The present invention provides an industrial process operating state evaluation method based on supervised probability slow feature analysis, comprising the following steps:

[0116] Step 1: Use the SPSFA algorithm to perform static-dynamic characteristic collaborative sensing information mining, and establish an offline evaluation model for running state evaluation;

[0117] S11: Collect the data generated during the production process and divide the data into the input matrix X ∈ R N×m and the output matrix Y∈R N , where N is the number of samples, m is the number of variables, R is the set of real numbers, and R N×m Represents a real matrix of N × m dimensions;

[0118] S12: Perform zero mean and unit variance processing on each column of the input matrix X, denoted as input matrix X a , and denote the difference between two consecutive input data points in time in each column as ΔX a ; Standardize ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an industrial process operation state evaluation method based on supervised probability slow feature analysis, which comprises the following steps of: 1, carrying out static-dynamic characteristic collaborative perception information mining by utilizing a supervised probability slow feature analysis algorithm, and establishing an off-line evaluation model of operation state evaluation, deep extraction of industrial process operation static-dynamic collaborative perception and operation state evaluation information is realized; and 2, calculating a score vector of online data according to the offline evaluation model, calculating static and first-order dynamic evaluation indexes and second-order dynamic indexes, and finally completing comprehensive evaluation of a process steady state, a hidden state, an unsteady state and a transition state. The method can effectively solve the problems that a traditional industrial process operation state evaluation method is inaccurate in process information extraction and lacks of evaluation of useless information in data, can achieve comprehensive evaluation of the process operation state, is more accurate in process state cognition, and can effectively reduce the probability of misinformation and missing report.

Description

technical field [0001] The invention belongs to the technical field of industrial production process operating state evaluation, and in particular relates to an industrial process operating state evaluation method based on supervised probability slow feature analysis. Background technique [0002] The safe and sustainable operation of the production process is the basis of process optimization and the basis of automation and intelligent manufacturing. However, in complex industrial processes such as mining, metallurgy and coal processing, uncertainties and disturbances often occur, making it impossible to operate stably for a long time near the optimal operating point, often requiring continuous manual intervention, making it difficult to ensure production efficiency and comprehensive economic benefits. Currently, traditional process monitoring only focuses on the occurrence of anomalies. Due to process disturbances and uncertainties, even under normal operating conditions...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G05B23/02
CPCG05B23/0243G05B2219/24065Y02P90/02
Inventor 褚菲葛茹许杨莫双双廖霜霜何大阔王福利
Owner CHINA UNIV OF MINING & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap